围产期动脉缺血性中风的危险因素:一种机器学习方法
Ratika Srivastava1, Lauran Cole1, Kimberly Amador1
1From the Division of Pediatric Neurology (R.S., L.C.), Department of Pediatrics, University of Alberta; Alberta Children's Hospital Research Institute and Department of Clinical Neurosciences (K.A.); Department of Clinical Neurosciences (N.D.F.); Department of Pediatrics and Clinical Neurosciences (M.D.), University of Calgary, Alberta; Departments of Pediatrics and Neurology/Neurosurgery (M.I.S., M.O.), McGill University, Montreal, Quebec, Canada; Newcastle upon Tyne Hospitals (A.P.B.), NHS Foundation Trust, Newcastle upon Tyne, United Kingdom; Department of Neurology (M.J.R.), Boston Children's Hospital and Department of Neurology, Harvard Medical School, Boston, MA; Department of Neonatology (E.S.), Soroka University Medical Center and Faculty of Health sciences, Ben-Gurion University of the Negev, Beer-Sheva, Israel; Department of Neonatology (L.S.V.), University Medical Center Utrecht, The Netherlands; Departments of Pediatrics and Community Health Sciences (D.D.), Owerko Centre at the Alberta Children's Hospital Research Institute, Hotchkiss Brain Institute, Cummings School of Medicine; Faculty of Nursing and Cumming School of Medicine (N.L.), Departments of Pediatrics, Psychiatry and Community Health Sciences; Alberta Children's Hospital Research Institute and Department of Clinical Neurosciences (P.M.); Departments of Clinical Neurosciences (M.D.H.), Community Health Sciences, Medicine and Radiology, Hotchkiss Brain Institute and Department of Pediatrics (A.K.), Cumming School of Medicine, University of Calgary, Alberta, Canada.
机器学习确定了围产动脉缺血性中风 (PAIS) 的关键临床因素,这是脑的主要原因. 这种数据驱动的方法准确地预测了新生儿的PAIS风险,优于传统模型.
科学领域:
- 神经学 神经学
- 儿科 儿科 儿科
- 数据科学数据科学数据科学
背景情况:
- 围产期动脉缺血性中风 (PAIS) 是半性脑的一个重要原因.
- 之前对PAIS预测因子的研究受限于样本大小和复杂的因子相互作用.
研究的目的:
- 将机器学习应用于大型数据集,以无偏见地识别PAIS临床预测因素.
- 将数据驱动的机器学习模型与PAIS的传统文献驱动的预测模型进行比较.
主要方法:
- 利用来自三个PAIS注册表和健康对照队列的共同数据元素.
- 采用了来自2571名新生儿 (527例,2044例对照) 的数据的随机森林机器学习管道.
- 在分析中包括了母亲/怀孕,产后和新生儿因素.
主要成果:
- 机器学习模型在预测PAIS方面实现了86.5%的平衡精度.
- 确定了关键预测因素,包括母亲的年龄,物质暴露,产后发烧和Apgar分数.
- 机器学习模型 (AUC 0.93) 的表现明显超过了基于文献的模型 (AUC 0.73).
结论:
- 机器学习为识别PAIS临床预测因子提供了一个公正的方法.
- 这些发现支持PAIS病理生理学的多因素性质.
- 使用这种方法可以识别患PAIS风险的新生儿.


